While our Installation & Getting Started page covers basic installation and simple examples of using the neural NLP pipeline, on this page we provide links to advanced examples on building the pipeline, running text annotation and converting the annotations into different formats. At the end we also link to toturials with online notebooks for interactive learning of the library.

Pipeline Building

Building a Neural Pipeline with Customized Model Paths

Text Annotation

Running Tokenization and Sentence Segmentation

Running Tokenization without Sentence Segmentation

Running Stanza with Pretokenized Text

Using spaCy for Fast Tokenization and Sentence Segmentation

Accessing Syntactic Words of Multi-Word Tokens

Accessing Parent Token of a Word

Accessing POS and Morphological Features of a Word

Accessing Lemma of a Word

Improving the Lemmatizer by Providing Key-Value Dictionary

Accessing Head and Dependency Relation of a Word

Running Dependency Parsing with Pre-annotated Document

Accessing Named Entities in a Sentence or a Document

Data Conversion

Document to Python Object

Python Object to Document

CoNLL to Python Object

Python Object to CoNLL

Interactive Tutorials

A Beginner’s Guide to Stanza

Using CoreNLP with Stanza